whatmodel.sh / image / FireRed-Image-Edit-1.1
FireRed-Image-Edit-1.1
↗ share
+ contribute
FireRed-Image-Edit-1.1 is an open-weights image model from FireRedTeam (Xiaohongshu), released March 2026. Licence: apache-2.0.
Catalogue identity notes
Xiaohongshu FireRedTeam's FireRed-Image-Edit-1.1 (FireRedTeam/FireRed-Image-Edit-1.1, pinned 3bc3f2a, Apache-2.0). ChartSync evaluates both 1.0 and 1.1 by name (Table 7: guidance 4.0, 40 steps). Lightning and ComfyUI repackagings are separate and not assumed. Comparison-only.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of FireRed-Image-Edit-1.1, out of 197 with a score, then more from FireRedTeam (Xiaohongshu).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 53 |  Wan 2.5 Text-to-Image Preview | 59±3 | api $0.030/image | ||
| 54 |  Recraft V4 | 59±3 | api $0.040/image | ||
| 55 | FireRed-Image-Edit-1.1 | 59±4 | comparison only | ||
| 56 |  Krea 2 Turbo | 59±3 | api $0.015/image +local | ||
| 57 |  GPT Image 1 Mini | 59±2 | api $0.011/image | ||
| more from FireRedTeam (Xiaohongshu) | |||||
| 75 | FireRed-Image-Edit-1.0 | 56±4 | comparison only | ||
$ what it's good at
image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #29 of 81 * · 23% of its score · 1 test
Beats FLUX.2 [max], FLUX.2 [pro], FLUX.2 [flex] here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MultiTextEdit cross-lingual text-in-image editing (SemAvg, LVM judge) | 64.1% ✎ | ▄·▄▄▄▄··█▄·▄ beats 5/8 | 23% |
other tests1 not in a task · 71% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ChartSync chart editing (Overall) | 56.2% ✎ | ▂··▂█▃▄▂▂·▂▂ beats 6/12 | 71% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/FireRedTeam ↗
$ how the score was worked out · ChartSync: A Benchmark for Vi… 71%, MultiTextEdit: Benchmarking C… 23%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1) | 1 | 71% |
| MultiTextEdit: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing (arXiv:2605.08163v2), Table 3 | 1 | 23% |
| prior · pull toward the middle | 6% | |
| weighted average | = 58.9 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json